2026 edition · Top 80
Machine learning foundations
Learning theory, statistics, optimisation and probabilistic modelling: the ideas the rest of the field stands on.
Learning theory & classic ML: 38 · Probabilistic ML: 34 · N = 80, scaled from 194 candidates.
0 of 80 of this page's 80 read · saved in this browser only
- 1
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Arthur P. Dempster · 50,453 citations · OpenAlex
Editor's note - 2
- 3
- 4
Equation of State Calculations by Fast Computing Machines
Nicholas Metropolis · 37,189 citations · OpenAlex
Editor's note - 5
- 6
A decision-theoretic generalization of on-line learning and an application to boosting
Yoav Freund · 20,464 citations · OpenAlex
Editor's note - 7
Monte Carlo sampling methods using Markov chains and their applications
W. K. Hastings · 15,193 citations · OpenAlex
Editor's note - 8
- 9
- 10
A Training Algorithm for Optimal Margin Classifiers
Bernhard Boser · 11,991 citations · OpenAlex
- 11
- 12
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
Stuart Geman · 17,953 citations · OpenAlex
Editor's noteClassic quota - 13
Understanding deep learning requires rethinking generalization
Chiyuan Zhang · 5,332 citations · Papers With Code
Editor's note - 14
Finite-time Analysis of the Multiarmed Bandit Problem
Peter Auer · 5,983 citations · OpenAlex
Editor's note - 15
- 16
Bagging Predictors
Leo Breiman · 17,788 citations · OpenAlex
- 17
- 18
- 19
Stochastic Variational Inference
Matthew D. Hoffman · 3,162 citations · Semantic Scholar
- 20
Greedy Function Approximation: A Gradient Boosting Machine
Jerome Friedman · 30,481 citations · OpenAlex
- 21
- 22
A New Approach to Linear Filtering and Prediction Problems
Rudolf E. Kalman · 31,615 citations · OpenAlex
Editor's note - 23
- 24
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Yarin Gal · 13,239 citations · Papers With Code
- 25
Regression Shrinkage and Selection Via the Lasso
Robert Tibshirani · 51,469 citations · OpenAlex
- 26
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Lakshminarayanan · 9,036 citations · Semantic Scholar
- 27
The central role of the propensity score in observational studies for causal effects
Paul R. Rosenbaum · 31,083 citations · OpenAlex
- 28
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
Vladimir Vapnik · 2,447 citations · OpenAlex
Editor's note - 29
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Qiying Yu · 2,948 citations · Papers With Code
- 30
Stan: A Probabilistic Programming Language
Bob Carpenter · 7,749 citations · OpenAlex
- 31
The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
Matthew D. Hoffman · 5,607 citations · Semantic Scholar
- 32
Hierarchical Dirichlet Processes
Yee Whye Teh · 3,476 citations · OpenAlex
- 33
Wan: Open and Advanced Large-Scale Video Generative Models
Team Wan · 2,890 citations · Papers With Code
- 34
Estimating the Dimension of a Model
Gideon Schwarz · 47,032 citations · OpenAlex
- 35
Factor Graphs and the Sum-Product Algorithm
Frank R. Kschischang · 6,486 citations · OpenAlex
- 36
Learnability and the Vapnik-Chervonenkis Dimension
Anselm Blumer · 1,820 citations · OpenAlex
Editor's note - 37
Statistical Modeling: The Two Cultures
Leo Breiman · 4,336 citations · OpenAlex
- 38
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
Zhuoyi Yang · 2,551 citations · Papers With Code
- 39
Local Computations with Probabilities on Graphical Structures and Their Application to Expert Systems
Steffen L. Lauritzen · 3,907 citations · OpenAlex
- 40
The Weighted Majority Algorithm
Nick Littlestone · 1,968 citations · OpenAlex
- 41
Hybrid Monte Carlo
Simon Duane · 4,026 citations · Semantic Scholar
- 42
Additive Logistic Regression: A Statistical View of Boosting
Jerome Friedman · 6,885 citations · OpenAlex
- 43
Stacked Generalization
David Wolpert · 7,946 citations · OpenAlex
- 44
Weight Uncertainty in Neural Network
Charles Blundell · 2,326 citations · Semantic Scholar
- 45
WebArena: A Realistic Web Environment for Building Autonomous Agents
Shuyan Zhou · 2,302 citations · Papers With Code
- 46
Machine Learning: A Probabilistic Perspective
Murphy · 9,062 citations · OpenAlex
- 47
A Practical Bayesian Framework for Backpropagation Networks
MacKay · 2,917 citations · OpenAlex
- 48
CatBoost: unbiased boosting with categorical features
7,236 citations · Semantic Scholar
- 49
Regularization and Variable Selection Via the Elastic Net
20,945 citations · OpenAlex
- 50
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
Danilo Jimenez Rezende · 6,329 citations · Semantic Scholar
- 51
No Free Lunch Theorems for Optimization
14,558 citations · Semantic Scholar
- 52
LLMs Get Lost In Multi-Turn Conversation
Philippe Laban · 527 citations · Papers With Code
- 53
Nonlinear Component Analysis as a Kernel Eigenvalue Problem
Bernhard Schölkopf · 8,092 citations · OpenAlex
- 54
Cross-Validatory Choice and Assessment of Statistical Predictions
M. Stone · 10,829 citations · OpenAlex
Editor's note - 55
Information Theory, Inference and Learning Algorithms
11,174 citations · Semantic Scholar
- 56
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
Peter Bartlett · 3,399 citations · Semantic Scholar
- 57
Bootstrap Methods: Another Look at the Jackknife
17,594 citations · OpenAlex
- 58
Extremely randomized trees
9,286 citations · OpenAlex
- 59
Probabilistic programming in Python using PyMC3
John Salvatier · 2,527 citations · OpenAlex
- 60
Sampling-Based Approaches to Calculating Marginal Densities
Alan E. Gelfand · 6,606 citations · OpenAlex
- 61
MCMC using Hamiltonian dynamics
Neal · 2,580 citations · OpenAlex
- 62
A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
Angelopoulos · 1,383 citations · Papers With Code
- 63
The Random Subspace Method for Constructing Decision Forests
7,130 citations · Semantic Scholar
- 64
On the Spectral Bias of Neural Networks
Nasim Rahaman · 2,853 citations · Semantic Scholar
- 65
Finding scientific topics
Thomas L. Griffiths · 6,047 citations · OpenAlex
- 66
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li · 589 citations · Papers With Code
- 67
Bayesian Learning via Stochastic Gradient Langevin Dynamics
Max Welling · 3,441 citations · Semantic Scholar
- 68
Bayesian Interpolation
David J. C. MacKay · 4,443 citations · OpenAlex
- 69
A Conceptual Introduction to Hamiltonian Monte Carlo
Betancourt · 1,517 citations · Papers With Code
- 70
Deep Double Descent: Where Bigger Models and More Data Hurt
Preetum Nakkiran · 1,213 citations · Papers With Code
- 71
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Zihan Qiu · 351 citations · Papers With Code
- 72
Information Theory and Statistical Mechanics
Edwin T. Jaynes · 12,938 citations · OpenAlex
- 73
Multivariate Adaptive Regression Splines
8,109 citations · OpenAlex
- 74
Learning Bayesian Networks: The Combination of Knowledge and Statistical Data
Heckerman · 3,252 citations · OpenAlex
- 75
Estimating causal effects of treatments in randomized and nonrandomized studies
Donald B. Rubin · 9,369 citations · OpenAlex
- 76
Asymptotically Efficient Adaptive Allocation Rules
T. L. Lai · 2,406 citations · OpenAlex
- 77
On Information and Sufficiency
Solomon Kullback · 20,191 citations · OpenAlex
- 78
Ridge Regression: Biased Estimation for Nonorthogonal Problems
13,710 citations · Crossref
- 79
Online Convex Programming and Generalized Infinitesimal Gradient Ascent
Martin Zinkevich · 2,914 citations · Semantic Scholar
- 80
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Maksym Andriushchenko · 508 citations · Papers With Code
Ranked on another page
Also relevant
Top 500 papers ranked on another domain page that matter here too.
The perceptron: A probabilistic model for information storage and organization in the brain
Frank Rosenblatt · 12,279 citations · OpenAlex
Editor's noteXGBoost: A Scalable Tree Boosting System
Tianqi Chen · 63,958 citations · Papers With Code
Variational Inference with Normalizing Flows
Danilo Jimenez Rezende · 5,182 citations · Papers With Code
AwardThe Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Jonathan Frankle · 4,519 citations · Papers With Code
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Arthur Jacot · 4,360 citations · Papers With Code
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0), and 
Semantic Scholar (used under its non-commercial API licence). Each count names its source. See the method.